The afternoon sun, usually a source of warmth, felt oppressive against Clara's skin. Across the country. Across the horizon. From Olivia. Olivia’s voice had been tight, her words a series of quick, clipped syllables. Clara sat down on the edge of the bed.

A deep fatigue settled in her bones, making each movement feel like an exercise in futility. She wanted nothing more than to curl up under the covers and disappear. She glanced at the clock, the passing seconds slow and deliberate.

She didn't know how she was going to get through the rest of the day, let alone the coming months. The thought of all the farewells, the packing, the goodbyes, felt like a mountain of stone.

Emotion: tired

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.92 Negative
PC2 (Disposition): -1.00

Role in Research

This story is one of 1,000 stories generated for the emotion tired. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 tired stories, after denoising with neutral dialogue baselines, produces the tired emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the tired vector is projected through the unembedding matrix.

Promoted:
weary0.254
fatigue0.249
😴0.238
sighed0.237
barely0.230
Suppressed:
C-0.268
because-0.225
B-0.219
🤟-0.217
భి-0.214